concept
active
concept:task-weight

Task weight

Coefficient weighting each task loss in the MTL objective.

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Weight spaceconcept0.784
    The space of the model's parameter matrices, where VPD operations take place.
  • Task Difficultyconcept0.766
    The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
  • Task balancingconcept0.761
    The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
  • Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
  • Weight Editingmethod0.755
    Editing network weights to test predictions about circuit function; proposed as falsifiability test for circuit claims
  • Equal Weightingframework0.741
    Baseline MTL approach minimizing sum of task losses with equal weights; suffers from task balancing
  • Logit weight contributions from a feature that arise due to superposition with other features, not from the feature's own causal role
  • scaleconcept0.726
    A formal context with a suggestive interpretation used in conceptual scaling.